Keystroke Dynamics Research Articles

Distinguishability of keystroke dynamic template.

When keystroke dynamics are used for authentication, users tend to get different levels of security due to differences in the quality of their templates. This paper addresses this issue by proposing a metric to quantify the quality of keystroke dynamic templates. That is, in behavioral biometric verification, the user's templates are generally constructed using multiple enrolled samples to capture intra-user variation. This variation is then used to normalize the distance between a set of enrolled samples and a test sample. Then a normalized distance is compared against a predefined threshold value to derive a verification decision. As a result, the coverage area for accepted samples in the original space of vector representation is discrete. Therefore, users with the higher intra-user variation suffer higher false acceptance rates (FAR). This paper proposes a metric that can be used to reflect the verification performance of individual keystroke dynamic templates in terms of FAR. Specifically, the metric is derived from statistical information of user-specific feature variations, and it has a non-decreasing property when a new feature is added to a template. The experiments are performed based on two public keystroke dynamic datasets comprising of two main types of keystroke dynamics: constrained-text and free-text, namely the CMU keystroke dynamics dataset and the Web-Based Benchmark for keystroke dynamics dataset. Experimental results based on multiple classifiers demonstrate that the proposed metric can be a good indicator of the template's false acceptance rate. Thus, it can be used to enhance the security of the user authentication system based on keystroke dynamics.

An Improved User Identification based on Keystroke-Dynamics and Transfer Learning

Transfer learning is one of the most appreciated classification techniques, when a small size of training dataset and limited computer capabilities exist along with the presence of noisy data. Such a scenario is encountered in keystroke dynamics whereby the typing gesticulation composed to form ‘keystroke dynamics’, is used to distinguish a human. Keystroke dynamics is persistently gaining reputation as one of the most promising and cost-effective behavioral biometrics. AlexNet and ResNet are two separate types of pre-trained convolutional neural network models, normally used to apply deep transfer learning concepts within image-based systems. Conversion of keystroke data into image data and then the formation of the artificial image data by extending available data are crucial attraction of this paper. In this paper, the pre-trained models are utilized by applying fine-tuning (of parameters in some layers) and used as an end-to-end learning and classification system by us. On the keystroke dataset, the feature extraction method (support vector machine for classification) is also applied here with pre-trained models. A relative analysis of both approaches is provided and lastly, the better one is employed in the proposed (recognition based) system. Finally, 98.57% accuracy of successful recognition is recorded.

Robust biometric system using session invariant multimodal EEG and keystroke dynamics by the ensemble of self-ONNs

Harnessing the inherent anti-spoofing quality from electroencephalogram (EEG) signals has become a potential field of research in recent years. Although several studies have been conducted, still there are some vital challenges present in the deployment of EEG-based biometrics, which is stable and capable of handling the real-world scenario. One of the key challenges is the large signal variability of EEG when recorded on different days or sessions which impedes the performance of biometric systems significantly. To address this issue, a session invariant multimodal Self-organized Operational Neural Network (Self-ONN) based ensemble model combining EEG and keystroke dynamics is proposed in this paper. Our model is tested successfully on a large number of sessions (10 recording days) with many challenging noisy and variable environments for the identification and authentication tasks. In most of the previous studies, training and testing were performed either over a single recording session (same day) only or without ensuring appropriate splitting of the data on multiple recording days. Unlike those studies, in our work, we have rigorously split the data so that train and test sets do not share the data of the same recording day. The proposed multimodal Self-ONN based ensemble model has achieved identification accuracy of 98% in rigorous validation cases and outperformed the equivalent ensemble of deep CNN models. A novel Self-ONN Siamese network has also been proposed to measure the similarity of templates during the authentication task instead of the commonly used simple distance measure techniques. The multimodal Siamese network reduces the Equal Error Rate (EER) to 1.56% in rigorous authentication. The obtained results indicate that the proposed multimodal Self-ONN model can automatically extract session invariant unique non-linear features to identify and authenticate users with high accuracy.

Improvised multi-factor user authentication mechanism using defense in depth strategy with integration of passphrase and keystroke dynamics

As the technology has emerged, the need for computer systems and computer networks has increased, and so has the requirement for authentication been escalated. Multi-Factor Authentication has been used since the past decade and still is the best type of authentication available to us today. The only disadvantage is the type of factors being used in the multi factor architecture and mechanism. If better and complex factors are not engaged in proper order or sequence in any multi-factor authentication, it can jeopardize the information systems and result in data, especially the digital identity of user, being compromised. On the note for improving authentication systems, the proposed work introduces a 3 factor authentication system with 3 levels of security. Each level being more secure than the last one, thus implementing a defense in depth strategy. Every level uses different factor for the purpose of authentication. The factors being used in the mechanism include a 4 digit passcode, passphrase, and keystroke dynamics. These factors are considered to be economical and easy to integrate in multi factor authentication. Further, the proposed work’s security strength has been evaluated with the help of Shannon’s entropy theory and is compared with other recent works on multi factor authentication. The proposed work is sought to provide a multi factor authentication mechanism which is economical and provides robust security in this emerging technological era.

Associations between smartphone keystroke dynamics and cognition in MS.

Examine the associations between smartphone keystroke dynamics and cognitive functioning among persons with multiple sclerosis (MS). Sixteen persons with MS with no self-reported upper extremity or typing difficulties and 10 healthy controls (HCs) completed six weeks of remote monitoring of their keystroke dynamics (i.e., how they typed on their smartphone keyboards). They also completed a comprehensive neuropsychological assessment and symptom ratings about fatigue, depression, and anxiety at baseline. A total of 1,335,787 keystrokes were collected, which were part of 30,968 typing sessions. The MS group typed slower (P < .001) and more variably (P = .032) than the HC group. Faster typing speed was associated with better performance on measures of processing speed (P = .016), attention (P = .022), and executive functioning (cognitive flexibility: P = .029; behavioral inhibition: P = .002; verbal fluency: P = .039), as well as less severe impact from fatigue (P < .001) and less severe anxiety symptoms (P = .007). Those with better cognitive functioning and less severe symptoms showed a stronger correlation between the use of backspace and autocorrection events (P < .001). Typing speed may be sensitive to cognitive functions subserved by the frontal-subcortical brain circuits. Individuals with better cognitive functioning and less severe symptoms may be better at monitoring their typing errors. Keystroke dynamics have the potential to be used as an unobtrusive remote monitoring method for real-life cognitive functioning among persons with MS, which may improve the detection of relapses, evaluate treatment efficacy, and track disability progression.

A Systematic Literature Review on Latest Keystroke Dynamics Based Models

The purpose of this study is to conduct a comprehensive evaluation and analysis of the most recent studies on the implications of keystroke dynamics (KD) patterns in user authentication, identification, and the determination of useful information. Another aim is to provide an extensive and up-to-date survey of the recent literature and potential research directions to understand the present state-of-the-art methodologies in this particular domain that are expected to be beneficial for the KD research community. From January 1st, 2017 to March 13th, 2022, the popular six electronic databases have been searched using a search criterion (&#x201C;keystroke dynamics&#x201D; OR &#x201C;typing pattern&#x201D;) AND (&#x201C;authentication&#x201D; OR &#x201C;verification&#x201D; OR &#x201C;identification&#x201D;). With this criterion, a total of nine thousand three hundred forty-eight results, including duplicates, were produced. However, one thousand five hundred forty-seven articles have been chosen after removing duplicates and preliminary screening. Due to insufficient information, only one hundred twenty-seven high-quality quantitative research articles have been included in the article selection process. We compared and summarised several factors with multiple tables to comprehend the various methodologies, experimental settings, and findings. In this study, we have identified six unique KD-based designs and presented the status of findings toward an effective solution in authentication, identification, and prediction. We have also discovered considerable heterogeneity across studies in each KD-based design for desktops and smartphones separately. Finally, this paper found a few open research challenges and provided some indications for a deeper understanding of the issues and further study.

Imbalanced Ensemble Learning in Determining Parkinson's Disease Using Keystroke Dynamics

Imbalanced Ensemble Learning in Determining Parkinson's Disease Using Keystroke Dynamics

Continuous Authentication with Feature-Level Fusion of Touch Gestures and Keystroke Dynamics for Deep Learning Performance Improvement

Continuous Authentication with Feature-Level Fusion of Touch Gestures and Keystroke Dynamics for Deep Learning Performance Improvement

KEYSTROKE DYNAMICS ANALYSIS USING MACHINE LEARNING METHODS

The primary objective of the paper was to determine the user based on its keystroke dynamics using the methods of machine learning. Such kind of a problem can be formulated as a classification task. To solve this task, four methods of supervised machine learning were employed, namely, logistic regression, support vector machines, random forest, and neural network. Each of three users typed the same word that had 7 symbols 600 times. The row of the dataset consists of 7 values that are the time period during which the particular key was pressed. The ground truth values are the user id. Before the application of machine learning classification methods, the features were transformed to z-score. The classification metrics were obtained for each applied method. The following parameters were determined: precision, recall, f1-score, support, prediction, and area under the receiver operating characteristic curve (AUC). The obtained AUC score was quite high. The lowest AUC score equal to 0.928 was achieved in the case of linear regression classifier. The highest AUC score was in the case of neural network classifier. The method of support vector machines and random forest showed slightly lower results as compared with neural network method. The same pattern is true for precision, recall and F1-score. Nevertheless, the obtained classification metrics are quite high in every case. Therefore, the methods of machine learning can be efficiently used to classify the user based on keystroke patterns. The most recommended method to solve such kind of a problem is neural network.

The Effects of Bipolar Disorder Risk on a Mobile Phone Keystroke Dynamics Based Biomarker of Brain Age.

Background: Research by our group and others have demonstrated the feasibility of using mobile phone derived metadata to model mood and cognition. Given the effects of age and mood on cognitive performance, it was hypothesized that using such data a model could be built to predict chronological age and that differences between predicted age and actual age could be a marker of pathology.Methods: These data were collected via the ongoing BiAffect study. Participants complete the Mood Disorders Questionnaire (MDQ), a screening questionnaire for bipolar disorder, and self-reported their birth year. Data were split into training and validation sets. Features derived from the smartphone kinematics were used to train random forest regression models to predict age. Prediction errors were compared between participants screening positive and negative on the MDQ.Results: Three hundred forty-four participants had analyzable data of which 227 had positive screens for bipolar disorder and 117 had negative screens. The absolute prediction error tended to be lower for participants with positive screens (median 4.50 years) than those with negative screens (median 7.92 years) (W = 508, p = 0.0049). The raw prediction error tended to be lower for participants with negative screens (median = −5.95 years) than those with positive screens (median = 0.55 years) (W = 1,037, p= 0.037).Conclusions: The tendency to underestimate the chronological age of participants screening negative for bipolar disorder compared to those screening positive is consistent with the finding that bipolar disorder may be associated with brain changes that could reflect pathological aging. This interesting result could also reflect that those who screen negative for bipolar disorder and who engaged in the study were more likely to have higher premorbid functioning. This work demonstrates that age-related changes may be detected via a passive smartphone kinematics based digital biomarker.

Keystroke dynamics Digital biomarkers of stress and alertness

Keystroke dynamics Digital biomarkers of stress and alertness

BioGames: a new paradigm and a behavioral biometrics collection tool for research purposes

PurposeThe purpose of this paper is to present a new paradigm, named BioGames, for the extraction of behavioral biometrics (BB) conveniently and entertainingly. To apply the BioGames paradigm, the authors developed a BB collection tool for mobile devices named BioGames App. The BioGames App collects keystroke dynamics, touch gestures, and motion modalities and is available on GitHub. Interested researchers and practitioners may use it to create their datasets for research purposes.Design/methodology/approachOne major challenge for BB and continuous authentication (CA) research is the lack of actual BB datasets for research purposes. The compilation and refinement of an appropriate set of BB data constitute a challenge and an open problem. The issue is aggravated by the fact that most users are reluctant to participate in long demanding procedures entailed in the collection of research biometric data. As a result, they do not complete the data collection procedure, or they do not complete it correctly. Therefore, the authors propose a new paradigm and introduce a BB collection tool, which they call BioGames, for the extraction of biometric features in a convenient way. The BioGames paradigm proposes a methodology where users play games without participating in an experimental painstaking process. The BioGames App collects keystroke dynamics, touch gestures, and motion modalities.FindingsThe authors proposed a new paradigm for the collection of BB on mobile devices and created the BioGames application. The BioGames App is an Android application that collects BB data on mobile devices and sends them to a database. The database design allows multiple users to store their sensor data at any time. Thus, there is no concern about data separation and synchronization. BioGames App is General Data Protection Regulation (GDPR) compliant as it collects and processes only anonymous data.Originality/valueThe BioGames App is a publicly available tool that combines the keystroke dynamics, touch gestures, and motion modalities. In addition, it uses a methodology where users play games without participating in an experimental painstaking process.

An Efficient Optimized Mouse and Keystroke Dynamics Framework for Continuous Non-Intrusive User Authentication

An Efficient Optimized Mouse and Keystroke Dynamics Framework for Continuous Non-Intrusive User Authentication

Smartphone-derived keystroke dynamics are sensitive to relevant changes in multiple sclerosis.

BackgroundTo investigate smartphone keystroke dynamics (KD), derived from regular typing, on sensitivity to relevant change in disease activity, fatigue, and clinical disability in multiple sclerosis (MS).MethodsPreplanned interim analysis of a cohort study with 102 MS patients assessed at baseline and 3‐month follow‐up for gadolinium‐enhancing lesions on magnetic resonance imaging, relapses, fatigue and clinical disability outcomes. Keyboard interactions were unobtrusively collected during typing using the Neurokeys App. From these interactions 15 keystroke features were derived and aggregated using 16 summary and time series statistics. Responsiveness of KD to clinical anchor‐based change was assessed by calculating the area under the receiver operating characteristic curve (AUC). The optimal cut‐point was used to determine the minimal clinically important difference (MCID) and compared to the smallest real change (SRC). Commonly used clinical measures were analyzed for comparison.ResultsA total of 94 patients completed the follow‐up. The five best performing keystroke features had AUC‐values in the range 0.72–0.78 for change in gadolinium‐enhancing lesions, 0.67–0.70 for the Checklist Individual Strength Fatigue subscale, 0.66–0.79 for the Expanded Disability Status Scale, 0.69–0.73 for the Ambulation Functional System, and 0.72–0.75 for Arm function in MS Questionnaire. The MCID of these features exceeded the SRC on group level. KD had higher AUC‐values than comparative clinical measures for the study outcomes, aside from ambulatory function.ConclusionsKeystroke dynamics demonstrated good responsiveness to changes in disease activity, fatigue, and clinical disability in MS, and detected important change beyond measurement error on group level. Responsiveness of KD was better than commonly used clinical measures.

On the shape of timings distributions in free-text keystroke dynamics profiles

Keystroke dynamics is a soft biometric trait. Although the shape of the timing distributions in keystroke dynamics profiles is a central element for the accurate modeling of the behavioral patterns of the user, a simplified approach has been to presuppose normality. Careful consideration of the individual shapes for the timing models could lead to improvements in the error rates of current methods or possibly inspire new ones. The main objective of this study is to compare several heavy-tailed and positively skewed candidate distributions in order to rank them according to their merit for fitting timing histograms in keystroke dynamics profiles. Results are summarized in three ways: counting how many times each candidate distribution provides the best fit and ranking them in order of success, measuring average information content, and ranking candidate distributions according to the frequency of hypothesis rejection with an Anderson-Darling goodness of fit test. Seven distributions with two parameters and seven with three were evaluated against three publicly available free-text keystroke dynamics datasets. The results confirm the established use in the research community of the log-normal distribution, in its two- and three-parameter variations, as excellent choices for modeling the shape of timings histograms in keystroke dynamics profiles. However, the log-logistic distribution emerges as a clear winner among all two- and three-parameter candidates, consistently surpassing the log-normal and all the rest under the three evaluation criteria for both hold and flight times.

Developing of keystroke dynamics analyzing systems using a presentation based on state contexts

This aim of the article is to discusses the main static and dynamic user identification methods by keystroke dynamics. As part of the research, a generalized way of representing the process of typing on the keyboard based on the sequential change of the keyboard state was proposed. The definition of the keyboard state context, which is the basis for the dynamic identification procedure, is formulated. The proposed approach will make it possible to apply a variety of static identification methods, significantly expanding the set of methods used for dynamic user identification by keystroke dynamics.

Predicting Age Group and Gender of Smartphone Users Using Keystroke Biometrics

This paper investigated the impact of various keystroke dynamics features on a predictive biometric system. In this paper, keystroke dynamics data of 50 individuals have been acquired using an open-source data software application on an Android smartphone. A total number of 21 commonly used keystroke dynamics features were extracted from the raw data. The collected data was used in training a Random Forest algorithm using four different training sample sizes while the remaining portion of the data was used for classification. The algorithm was then used to determine the importance of 21 different keystroke dynamics features. The results showed that each features offers varying degree of importance in age-group and gender predictions. While such efforts have been made in the area of predictive keystroke dynamics using computer keyboards, literature on the same topic using touchscreen smartphone virtual keyboards have been limited.

Methods of long-term and short-term adaptation for biometric image of keystroke dynamics

This article discusses one of the main problems of user identification by keyboard handwriting - short-term changes in the keystroke dynamics of users in connection with its psychophysical state, as well as changes over a long time associated with the formation of keystroke dynamics by a new user or when switching to a new device. A method for determining the phase of working capacity by the time characteristics of the keystroke dynamics is proposed.

Keystroke Dynamics-Based Authentication System Using Empirical Thresholding Algorithm

In a password-based authentication technique, whenever the typed password and username matches the system database, the secure login page allows the client to access it. Despite the password matching, the proposed method checks the similarity between the typing rhythm of entered password and the rhythm of password samples in client's database. In this paper, a novel algorithmic procedure is presented to authenticate the legal client based on empirical threshold values obtained from the timing information of the client's keystroke dynamics. The exploratory outcomes demonstrate an impressive diminish in both false rejection rate and false acceptance rate. Equal error rate and authentication accuracy are also assessed to show the superiority and robustness of the method. Therefore, the proposed keystroke dynamics-based authentication method can be valuable in securing the system protection as a correlative or substitute form of client validation and as a useful resource for identifying the illegal invasion.

High-performance keyboard typing motion driven hybrid nanogenerator

Keyboard is the most common input device in computer and human-machine interface devices. Each keystroke during keyboard typing provides a huge amount of biomechanical energy that can be converted into useful electrical energy. Herein, we propose a high-performance electromagnetic-triboelectric hybrid nanogenerator for harvesting biomechanical energy from keyboard typing motion (KTMEH). Combining the effects of electromagnetic induction and triboelectric contact electrification, the KTMEH can simultaneously scavenge mechanical energy from keystroke motion and deliver a maximum power of 7.04 mW from electromagnetic and 1.8 mW from the triboelectric unit, from a single Typewriter key. The output performances were analyzed for different typing speeds, typing force, and key shapes. For an average typing speed of 4 characters per second (CPS), the KTMEH can scavenge a power of 5.6 mW and 1.5 mW from the electromagnetic and triboelectric unit, respectively. This hybrid configuration and highly miniaturized design enable versatile energy harvesting capability from existing commercial keyboards along with facile installation and durability. From the experimental results, it was found that the harvesting typing motion energy is capable to charge the capacitor and drive commercial electronic loads such as a hygrometer. This work expresses notable advantages of hybrid nanogenerators to develop next-generation self-powered keyboards, self-powered keystroke dynamics monitoring and sensing systems, and security systems with biometric authentication. • A high-performance keyboard typing motion-driven hybrid nanogenerator is presented. • Contact-separation of nano-wires and nanowires improves triboelectric performance by six times. • A single key can deliver a maximum power of 7.04 mW from a single keystroke. • Output performance was analyzed for different typing speeds, typing force, and key shapes. • The proposed hybrid nanogenerator can be easily installed on commercial keyboards.